Systems and methods for monitoring persons in a facility

Abstract

A system, comprising a plurality of wearable devices configured to be worn on a person's body, each wearable device comprising a microphone, a speaker and an antenna; a plurality of remote communication gateways and configured to enable transfer of the wireless signals from the antenna to a server and vice versa; and a server, comprising: a communication gateway configured to exchange signals with the multiple remote communication gateways; a memory for storing identifiers of a list of wearable devices and a remote communication gateway of the multiple remote communication gateways associated with each of the multiple wearable devices; and a processor configured to: convert an audio signal received from a specific wearable device of the multiple wearable devices into text data; identify a task from the textual data; and create a feedback message to be sent to the specific wearable device via the specific remote communication gateway.

Description

SYSTEMS AND METHODS FOR MONITORING PERSONS IN A FACILITYFIELD AND BACKGROUND

[0001] The invention, in some embodiments thereof, relates to monitoring persons using wearable devices.

[0002] Patients in hospitals and clinics often require monitoring and personnel attention and service, patients mainly use alarm buttons placed close to the hospital beds, which incur load on the nurses that receive the calls initiated by the alarm buttons. Some of the services handled by the nurses in response to receiving the calls from the alarm buttons can be handled by other hospital departments.SUMMARY

[0003] In accordance with exemplary embodiments, a system, comprising a plurality of wearable devices configured to be worn on a person's body, each wearable device comprising a microphone, a speaker and an antenna; a plurality of remote communication gateways and configured to enable transfer of the wireless signals from the antenna to a server and vice versa; and a server, comprising a communication gateway configured to exchange signals with the multiple remote communication gateways; a memory for storing identifiers of wearable devices and a remote communication gateway of the multiple remote communication gateways associated with each of the multiple wearable devices; and a processor configured to: convert an audio signal received from a specific wearable device of the multiple wearable devices into text data; identify a task from the textual data; and create a feedback message to be sent to the specific wearable device via the specific remote communication gateway.

[0004] In some cases, the specific remote communication gateway estimates the location of the specific wearable device. In some cases, the processor generates a command message to be sent to a target account related to execution the task, wherein the command message comprises an identifier of the location. In some cases, the specific remote communication gateway estimates the location based on signal strength and angle of arrival of the signal sent from the specific wearable device. In some cases, the feedback message is an audio message.In some cases, the task is identified as related to a medical condition and wherein the feedback message is created according to a treatment protocol for the identified medical condition. In some cases, the processor is configured to identify whether the received audio signal relates to a new task or relates to a current task. In some cases, the multiple wearable devices perform a roaming protocol configured to enable the multiple remote communication gateways to identify the wearable devices associated with each remote communication gateway.

[0005] In some cases, each wearable device comprising an accelerometer, wherein the server generates a falling event message in response to detection of abnormal readings by the accelerometer, wherein the server sends the falling event message to the wearable device that sent the abnormal reading, and wherein when the server identifies an insufficient response event from the wearable device the server sends an emergency message to an emergency account configured to handle a falling event.

[0006] A method, comprising collecting audio signals from wearable devices via remote communication gateways; converting the audio signal received from a specific wearable device of the multiple wearable devices into text data; identifying a task from the textual data; creating a feedback message to be sent to the specific wearable device via the specific remote communication gateway; generating a command message to be sent to a target account related to execution the task, wherein the command message comprising an identifier of the location.

[0007] In some cases, the method comprising identifying whether the message relates to a new task or old task. In some cases, the method comprising identifying similar requests in the person's history in a requests database; monitoring time elapsing from the similar request to the received message; in case the elapsing time is within a time frame of the person's medical condition, identify the message as relating to the similar request. In some cases, the method comprising computing the similarity between the extracted request and the request in the requests database by inputting vectors that represent text into a software model.

[0008] In some cases, identifying the similar request in case the similarity value between the extracted request and the request in the requests database is higher than a threshold. Insome cases, the method comprising determining an urgency level of the extracted request based on a series of messages from the wearable device compared to a medical protocol and medical history of the patient. In some cases, the method comprising generating a falling event message in response to detection of abnormal readings by the accelerometer, sending the falling event message to the wearable device that sent the abnormal reading, identifying an insufficient response event from the wearable device, sending an emergency message to an emergency account configured to handle a falling event.

[0009] A system, comprising a communication gateway configured to exchange signals with a plurality of wearable devices via multiple remote communication gateways; a memory for storing identifiers of a list of wearable devices and a remote communication gateway of the multiple remote communication gateways associated with each of the multiple wearable devices; a processor configured to convert an audio signal received from a specific wearable device of the multiple wearable devices into text data; identify a task from the textual data; and create a feedback message to be sent to the specific wearable device via the specific remote communication gateway.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Some embodiments of the invention are herein described, by way of example only, with reference to the accompanying drawings. With specific reference now to the drawings in detail, it is stressed that the particulars shown are by way of example and for purposes of illustrative discussion of embodiments of the invention. In this regard, the description taken with the drawings makes apparent to those skilled in the art how embodiments of the invention may be practiced.

[0011] In the drawings :

[0012] Figure 1 shows a computerized system having separate parties that take part in a process for assisting and monitoring persons in a facility, in accordance with some embodiments of the subject matter;

[0013] Figure 2 shows a server configured to monitor and provide service to the persons that use the wearable devices, in accordance with exemplary embodiments;

[0014] Figure 3 shows a wearable device configured to be worn by a person, in accordance with exemplary embodiments;

[0015] Figure 4 shows a method of exchanging information between a server and wearable devices, in accordance with exemplary embodiments;

[0016] Figure 5 shows a method of handling tasks by a server based on data received from wearable devices, in accordance with exemplary embodiments;

[0017] Figure 6 shows a method of executing a medical protocol by a server based on data received from wearable devices, in accordance with exemplary embodiments;

[0018] Figure 7 shows a method of handling a falling event by a server based on data received from wearable devices, in accordance with exemplary embodiments;

[0019] Figure 8 shows a method of identifying whether data received from wearable devices relates to a new task or a current task, in accordance with exemplary embodiments.DETAILED DESCRIPTION

[0020] At least some implementations described herein address the technical problem of inefficient nurse-calling systems in which a device operated by the nursing staff receives calls from patients via phones / buttons placed near the patients' beds. These nurse-calling systems handle all the calls with equal priority and without context before the nurses receive the call. This leads to delays in communication and response to patients' needs. These nursecalling systems do not process the calls before the calls are handled by the nurse, hence all the calls are processed regardless to urgency, resulting in all patient requests being treated with equal priority, preventing urgent treatment to patients that actually need it. This one- size-fits-all approach fails to optimize nurse response times and does not account for the varying levels of patient needs, from critical care to basic assistance. The system of embodiments herein can be used for other purposes in addition to nurse-calling systems, forexample in airports, hotels, factories, shopping malls and more. The system enables asynchronous handling of tasks by persons in the facility.

[0021] Further, when the patient is required to move from department to another department in the hospital, the patient will use a new phone / button coupled to the wall in the new department, or via wireless devices in a format similar to a walkie-talkie device. In such a case, the nurse that receives the call is unaware of the patient's identity, and there is no central entity that is aware of the patient's location.

[0022] Embodiments include a system having wearable devices used by person in a facility, for example patients in a hospital, and also to students, employees, customers and similar groups of persons. The facility may be a building, a complex of a plurality of buildings, a combination of buildings and open areas such as gardens, one or more gardens, and the like. The wearable devices communicate with a server via audio signals, for example using audio streaming. The server may analyze the audio signals, hence reducing load from the personnel, such as nurses, and addresses requests based on priority that are defined based on hospitals' protocols and medical protocols. In addition, the wearable devices may enable the server to identify the persons' location, as the persons are identified by the identifier of the wearable device. While embodiments are described as being in a facility, embodiments may work in different areas, within or outside of a building.

[0023] Figure 1 shows a computerized system having separate parties that take part in a process for assisting and monitoring persons in a facility, in accordance with some embodiments of the subject matter. The facility may be a university, a cruise ship, a hotel, an airport, a factory and similar institutes.

[0024] The computerized system may include wearable devices such as devices 110, 112, 115 configured to be worn on a person's body. Each wearable device of devices 110, 112, 115 comprising a microphone for collecting audio signals, a speaker for outputting audio signals and an antenna configured to enable exchange of wireless signals. The wearable devices 110, 112, 115 may be coupled to a person's limb, arm, finger, neck, head, leg and the like. The wearable devices 110, 112, 115 may be worn by securing the wearable devices 110,112, 115 to the persons' clothes, for example using adhesives, screws, pins other connection techniques, tools and mechanisms.

[0025] The computerized system may include one or more remote communication gateways 120, 125 disposed in a building and configured to enable transfer of the wireless signals from the antennas of the wearable devices 110, 112, 115 to a server and vice versa. The communication between the remote communication gateways 120, 125 and the antennas of the wearable devices 110, 112, 115 may be wireless, for example over Wi-Fi or cellular communication. The communication between the remote communication gateways 120, 125 and the server 130 may be wireless or wired. One remote communication gateway can provide a plurality of wearable devices to the server. For example, remote communication gateway 120 is the gateway for communication between the server 130 and wearable devices 110, 112 while the remote communication gateway 125 is the gateway for communication between the server 130 and wearable device 115.

[0026] In some exemplary cases, the remote communication gateways 120, 125 estimate the location of the wearable devices. The estimation may be performed based on signal strength (for example RS SI techniques) and Angle of Arrival (Ao A) of the signal sent from the wearable devices. In such cases, the remote communication gateways 120, 125 include a processor and memory for storing a set of instructions to be executed by the processor. In some cases, a plurality of remote communication gateways receives signals from the antenna of a wearable device, and the remote communication gateway that measured the stronger signal may be defined as associated with the wearable device in the memory of the server 130. In some exemplary embodiments, the wearable devices 110, 112 utilize roaming technology that allows the wearable devices 110, 112 to maintain continuous communications with the remote communication gateways and the server while roaming. For example, wearable device 110 may communicate with remote communication gateway 120 and then continue communication with remote communication gateway 125.

[0027] The computerized system may include a server 130 configured to monitor and provide service to the persons that use the wearable devices 110, 112, 115. The server 130 operates in response to receiving messages from the wearable devices 110, 112, 115. Theserver 130 may include a central communication gateway configured to exchange signals with the multiple remote communication gateways 120, 125 and a memory for storing identifiers of a list of wearable devices 110, 112, 115 and a remote communication gateway of the multiple remote communication gateways 120, 125 associated with each of the multiple wearable devices 110, 112, 115.

[0028] The server 130 may also include a processor configured to convert the audio signals received from a specific wearable device of the multiple wearable devices into text data, identify a task from the textual data and create a feedback message to be sent to the specific wearable device via the specific remote communication gateway. The processor may execute a set of rules, techniques and algorithms to implement the methods disclosed herein.

[0029] Figure 2 shows a server configured to monitor and provide service to the persons that use the wearable devices, in accordance with some embodiments of the subject matter.

[0030] The server 200 may include a central communication gateway 210 configured to exchange signals with the multiple remote communication gateways. The central communication gateway 210 may employ wired or wireless communication protocols, techniques and processes, such as Wi-Fi, cellular communication, Blue-Tooth and additional communications components.

[0031] The server 200 may include a memory 220 configured to store information on a computerized medium. The memory 220 may be a hard disk drive, a Flash disk, a Random Access Memory (RAM), a memory chip, and additional memory storage components. The memory 220 may be configured for storing identifiers of a list of wearable devices and a remote communication gateway associated with each of the multiple wearable devices. This way, when the server 200 sends a signal to a specific wearable device, the message may be sent to the specific remote communication gateway associated with the specific wearable device. The memory 220 may also be configured to store a set of rules executed by the processor. The memory 220 may also be configured to store one or more treatment protocols for the various medical events.

[0032] The server 200 may include a processor 230 configured to manage and execute the processes described herein, for example executing modules such as text to speech converter 240 or message generator 250. Processor 230 may be any one or more processors such as a Central Processing Unit (CPU), a microprocessor, an electronic circuit, an Integrated Circuit (IC), or the like. Processor 230 may be utilized to perform computations required by the apparatus or any of its subcomponents.

[0033] The server 200 may include a text to speech converter 240 configured to convert audio messages received from the wearable messages into text. The text to speech converter 240 may also be used to convert text messages created or selected by the server 200 into audio messages sent back to the wearable device. The text to speech converter 240 may employ speech recognition technologies such as Deep feedforward, recurrent neural networks, hidden Markov models, and additional speech recognition options.

[0034] The server 200 may include a message generator 250 configured to generate messages. The message generator 250 may generate messages in a text format or audio format. The message generator 250 may generate feedback message to be sent to the specific wearable device via the specific remote communication gateway.

[0035] In some exemplary embodiments, message generator 250 further generates a command message to be sent to a target account related to execution the task, wherein the command message may include an identifier of the location. The target account may be, or be identified by, a phone number, an email address, social network account or another account identifier input into the server 200, such as application programming interface (API) of another system. For example, Enterprise resource planning (ERP) and Electronic Medical Record (EMR) may be used.

[0036] Figure 3 shows a wearable device configured to be worn by a person, in accordance with some embodiments of the subject matter.

[0037] The wearable device 300 may include a body 310 configured to be secured to the person's body or the person's other objects, such as clothing, headset and the like. The body 310 may be bent to at least partially encircle the person's limb, neck, head and the like. Insome cases, the body 310 may include a connector, such as pins, buttons, screws, holes and the like, enabling connecting the body 310 to the patient's body or object. The wearable device 300 may include a controller 315 configured to control the processes performed by the wearable device 300. The controller 315 may comprise a processor and a memory configured to store a set of rules executed when the processes are performed.

[0038] The wearable device 300 may include a speaker 320 configured to output audio signals. The wearable device 300 may include a microphone 330 configured to detect audio signals. The wearable device 300 may include a sensor 340 configured to collect measurements. The sensor 340 may be a motion sensor, such as accelerometer, gyroscope and additional sensors.

[0039] The wearable device 300 may include an antenna 350 configured to exchange wireless signals to be sent to the server. The antenna 350 may employ wireless communication techniques, such as Wi-Fi, cellular communication, Blue-Tooth and additional communications components. The wearable device 300 may include a power source 360, such as a battery, interface for a cable transferring electrical power, a rechargeable battery, a solar panel and the like. The wearable device 300 may also include a push button 370 configured to enable the wearable device 300 to identify that the person wearing the wearable device 300 begins transmission of a message to the server. The wearable device 300 may also include an indicator, for example LED for visual indication. The wearable device 300 may also include a second antenna configured to exchange wireless signals during a process of locating the wearable device 300 or identifying the wearable device 300.

[0040] The antenna 350 may transmit secondary wireless signals intermittently, for example once every 2 seconds. The secondary wireless signals include an identifier of the person wearing the wearable device 300 and are sent regardless of audio messages sent by the person. The secondary wireless signals are received by electronic devices carried by employees of the organization, hence enabling the employees to identify the person. The secondary wireless signals enable the employee to obtain the person's identity when the person needs to receive medications, go through lab tests, operation, etc. The electronicdevice used by hospital personnel may communicate with the server to request information about the person wearing the wearable device. The electronic device may also communicate with the server and request other hospital personnel to perform a task, request for assistant, and the like. The wearable device may also comprise an amplifier coupled to the microphone and the speaker, and an indicator, such as visual indicator or a vibrating indicator.

[0041] Figure 4 shows a method of exchanging information between a server and wearable devices, in accordance with exemplary embodiments.

[0042] In operation 410 a message from wearable device may be received via remote communication gateway. The message may be in an audio format collected by a microphone included in the wearable device. The received signal may include an identification data of the wearable device, for example device #42. The received signal may also include a location of the wearable device, for example "room #21", "second floor" etc. The audio signal may be received over the internet, a local network, cellular communication or via other communication networks, protocols and components.

[0043] In operation 420 the audio signal may be converted into text data. The conversion may be done using speech recognition technologies such as Deep feedforward, recurrent neural networks, hidden Markov models, and other speech recognition systems. The text may be sent to a central device, such as a nursing desk or a security desk.

[0044] In operation 430 a task may be identified from the textual data. The task may be related to a medical condition, such as aches and fever. The task may relate to an object or condition, such as "towel" and "blanket" or a condition, such as "cold", "hot", "unpleasant smell". Identifying may be done using text analysis techniques or tools such as language models or other text analysis techniques. The task may be related to another condition included in the organization's workflow, for example a security condition, a technical condition such as failure or malfunction or a device, and the like.

[0045] When the textual data is analyzed by the server, the server may determine whether the message includes a task or not. A message without a task may be an error audio signal, a patient thanking the nurse and additional options. After determining that the messageincludes a task, the server may classify the task according to definitions of the organization utilizing the server. For example, the organization is a hospital, and the classes may be medical / service / comfort. The organization may be an airport, and the classes for an airport may be flight / service / maintenance / security. The server stores the workflows, sets of rules and decision trees dictated by the organization and adjusts the software algorithms according to the workflows. For example, the organization may dictate that when the audio message from the wearable device includes the word "eight" (8) in response to a message asking the person his / her level of pain, the task is defined as "high" and all nurses and doctors in the same department will receive a message to visit the patient. Other organizations may dictate that audio message from the wearable device includes the word "eight" (8) result in urgency status of "low" and sending a message to a single device only.

[0046] The server may determine the urgency level of the task based on a series of messages from the wearable device compared to a medical protocol and medical history of the patient wearing the wearable device. For example, in case the patient had a knee surgery and complaints on a headache with pain level "6", the urgency level of the message is lower than a patient that had a heart surgery and complaints on a headache with pain level "6".

[0047] The organization's workflows may differ from one department to another. For example, the same message or sequence of messages from the wearable device will result in a different message to be created and sent from the server, according to different workflows used in the different departments. The organization's workflows may also dictate that the status of a request changes over time, in case the request is not handled. For example, a request for a blanket may be considered "urgent" 2 hours after receipt of the first message that generated the task, or after 3 messages considered as related to the same task.

[0048] In operation 440 a feedback message may be created to be sent to the specific wearable device via the specific remote communication gateway. The feedback message may be selected from a list of messages based on the identified task. The feedback message may be sent in an audio format to be outputted via the speaker of the wearable device. The content and structure of the feedback message may be defined by the organization's workflows. Thefeedback message may be converted from text format into an audio message sent back to the wearable device.

[0049] In operation 450 a command message may be generated to be sent to a target account related to execution of the task. The target account may be a phone number, an email address, social network account or another account inputted into the server 200 such as API of another system. For example, EMR or ERP may be used. The command message may include an identifier of the wearable device, an identifier of the person wearing the wearable device, location of the wearable device, identification of the task, the medical condition of the person wearing the wearable device and a combination thereof. The content and structure of the command message may be defined by the organization's workflows, with placeholders that may be inputted based on the content of the message, for example the feedback provided by the person wearing the wearable device, a number of messages received about the task, and additional information. The command message may be converted from text format into an audio message sent back to the wearable device.

[0050] Figure 5 shows a method of handling tasks by a server based on data received from wearable devices, in accordance with exemplary embodiments.

[0051] In operation 510 a message from wearable device may be received. The message may be in an audio format collected by a microphone included in the wearable device. The received signal may include an identification data of the wearable device, for example device #42. The received signal may also include a location of the wearable device, for example "room #21", "second floor" etc. The audio signal may be received over the internet, a local network, cellular communication or other communications components, protocols, networks and tools.

[0052] In operation 520 it is identified whether the patient initiates a new task or checks on a prior task. An example of this process is further explained in Fig. 8. A new task may be a task that requires handling a condition or object that were not mentioned in a previous task during a predetermined period of time, for example 2 hours. In case the same person sends additional messages via the wearable device about the same subject, the server will not create a new task in the database and may send a secondary feedback message to the wearabledevice from which the message was sent. The secondary feedback message may be a message sent when the person sends multiple messages that relate to the same task.

[0053] In operation 530 a new task may be generated in the database. The new task may be generated in case the message is not defined as related to a previous task during a predetermined period of time. The predetermined period of time may vary depending on the nature of the task or the patient, for example in heart-related conditions the predetermined period of time will be shorter than in orthopedic conditions. The new task may include an identification of the person wearing the wearable device from which the message was sent, time of receipt of the message, person or department assigned to execute the task and the like.

[0054] In operation 540 a command message may be created and sent to the patient or the personnel in charge of patient. In some exemplary cases, the command message may include an identifier of the location of the wearable device, for example "room #13" or "near remote communication gateway #701".

[0055] Figure 6 shows a method of executing a medical protocol by a server based on data received from wearable devices, in accordance with exemplary embodiments.

[0056] In operation 610 the message may be identified as related to a medical condition. Identifying may be performed after converting the message from speech to text. Identifying may be performed by searching for key words in the text format of the message. Identifying may be performed by applying a similarity function between the words in the text format and words that represent medical conditions. Identifying may be performed by using semantic search or by using embeddings methodologies.

[0057] In operation 620 a message may be created according to treatment protocol of the medical condition. The memory of the server, or a memory accessible to the server, stores one or more treatment protocols. The treatment protocols include messages to be sent to the wearable devices. Some of the messages in the treatment protocols are conditional and sent only upon receipt of specific information included in the messages from the wearable device. For example, in case the person complains about headaches, the protocol will include a firstset of messages that may be different from a second set of messages sent in case the person complains of coughing. The messages may include questions and inquiries for the patient with the wearable device.

[0058] In operation 630 a deviation in the treatment protocol may be identified. The deviation may be identified based on data extracted from the messages received from the wearable devices, either from the messages' content, time elapsing between the messages, audio patterns such as variations in amplitude and additional parameters.

[0059] In operation 640 an alert message may be sent to an account operated by personnel in charge of the patient indicating the deviation. The alert message may be sent to an email address, a phone number, via a dedicated software application, and additional destinations.

[0060] Figure 7 shows a method of handling a falling event by a server based on data received from wearable devices, in accordance with exemplary embodiments.

[0061] In operation 710 readings from an accelerometer coupled to the wearable device may be collected. The accelerometer may collect readings in a sampling rate of 0.5-100 samples per second, or at another optional rate. The readings may be sent from the wearable device's antenna to the server.

[0062] In operation 720 discloses abnormal readings by the accelerometer may be detected. The abnormal readings may be higher than a threshold, for example higher than 2.5 m / s2. The threshold may vary from one person to another, for example based on age, medical condition and additional parameters. Abnormal readings may be a result of an error in the sensor or in the communication devices, or regular activities, and they may also indicate a falling event.

[0063] In operation 730 discloses falling event message may be generated in response to detection of abnormal readings by the accelerometer. The falling event message may be sent in an audio format. The falling event message may include the name of the person wearing the wearable device with the accelerometer that collected the abnormal readings. The falling event message may be "john, are you ok?".

[0064] In operation 740 the falling event message may be sent to the wearable device that sent the abnormal reading. The falling event message may be sent to the remote communication gateway associated with the wearable device of the abnormal readings.

[0065] In operation 750 an insufficient response event from the wearable device may be identified. Insufficient response may be lack of response for a predefined time, such as 10 seconds. Insufficient response may be receipt of an unclear audio signal, in a manner that the text to speech converter cannot recognize text from the audio signal. Examples of sufficient response from the wearable device may include "I fell" or "I'm ok".

[0066] In operation 760 an emergency message may be sent to an emergency account configured to handle a falling event. The emergency message may include a name of the person wearing the wearable device from which the abnormal readings were sent and the wearable device's location. The emergency message may also include a name of the person, medical condition and additional information such as age.

[0067] Figure 8 shows a method of identifying whether data received from wearable devices relates to a new task or a current task, in accordance with exemplary embodiments. A new task may be defined as an event in which the message from the wearable device is a first message in a predefined time frame that either informs of a medical condition or requires service, for example an object such as a blanket or a nurse visit. The predefine time frame may vary based of properties such as location, persons carrying the wearable device, departments in the facility, type of task and additional properties. A message relating to a current task is a message that requires the same service or informs of the same medical condition as received from the same wearable device in previous messages during the predefined time frame. For example, in case of receiving a message requesting a towel or water, 5 minutes after a prior message from the same wearable device that requested the same object, the message will be identified as related to a current task. As such, no new task will be added to the facility's database.

[0068] In operation 810 an audio message may be received from a wearable device worn by a person. The person may be a patient in a hospital. The audio message may be sent via a streaming format collected by a microphone included in the wearable device. The audiosignal may be received over the internet, a local network, cellular communication and additional communication protocols, networks, tools and components.

[0069] In operation 820 the audio message may be converted to text. The conversion may be done using speech recognition technologies such as Deep feedforward, recurrent neural networks, hidden Markov models, and other speech recognition methods.

[0070] In operation 830 a request may be extracted from the text. The request may relate to a medical condition or to a specific object, such as a towel, blanket, food product, medical device and the like. The request may be extracted from a list of requests. The request may be extracted using a language model such as Bidirectional encoder representations from transformers (BERT).

[0071] In operation 840 similar requests may be identified in the person's history in requests database. The similarity may be computed by inputting vectors that represent text into a software model. The similarity may be computed according to statistical analysis on the extracted request and other requests stored in the requests database. A similar request may be identified in case the similarity value between the extracted request and a request in the database is higher than a threshold.

[0072] In operation 850 the time stamp of the similar request may be checked, to detect whether the similar request was received during a time frame of the task. The time frame may differ according to various properties, such as type of the tasks, person's medical conditions and the like. For example, when a person requests a towel, the time frame of relating both requests to the same task may be 30 minutes, while when requesting a doctor, the time frame of relating both requests to the same task may be 5 minutes.

[0073] In operation 860 the message may be identified as a new task. This step is performed in case there is no request in the requests database that is sufficiently similar to the request extracted from the audio message. This step may also be performed in case another request was found similar to the extracted request, but the other request was received at a timestamp that exceeds a time interval that enables relating both requests to the same task. Upon identifying a new task, the server generates a message sent to the wearable device,indicating that the task is being handled. The message may be selected based on the time stamp of the previous request from the person.

[0074] In operation 870 the message may be identified as related to a current task. This step is performed in case there is another request in the requests database that is sufficiently similar to the request extracted from the audio message and the other request was received at a timestamp that lower a time interval that enables relating both requests to the same task. For example, when the time frame for the task is 20 minutes, the message was received 12 minutes after the former message related to the same task.

[0075] The descriptions of the exemplary embodiments have been presented for purposes of illustration but are not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the embodiments, the practical application or technical improvement over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

[0076] It is expected that during the life of a patent maturing from this application many relevant files and / or records will be developed and the scope of the term file and / or record is intended to include all such new technologies a priori.

[0077] As used herein the term “about” refers to ± 10 %.

[0078] The terms "comprises", "comprising", "includes", "including", “having” and their conjugates mean "including but not limited to". This term encompasses the terms "consisting of' and "consisting essentially of'.

[0079] The phrase "consisting essentially of' means that the composition or method may include additional ingredients and / or steps, but only if the additional ingredients and / or steps do not materially alter the basic and novel characteristics of the claimed composition or method.

[0080] As used herein, the singular form "a", "an" and "the" include plural references unless the context clearly dictates otherwise. For example, the term "a compound" or "at least one compound" may include a plurality of compounds, including mixtures thereof.

[0081] The word “exemplary” is used herein to mean “serving as an example, instance or illustration”. Any embodiment described as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments and / or to exclude the incorporation of features from other embodiments.

[0082] The word “optionally” is used herein to mean “is provided in some embodiments and not provided in other embodiments”. Any particular embodiment may include a plurality of “optional” features unless such features conflict.

[0083] Throughout this application, various embodiments may be presented in a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the invention. Accordingly, the description of a range should be considered to have specifically disclosed all the possible subranges as well as individual numerical values within that range. For example, description of a range such as from 1 to 6 should be considered to have specifically disclosed subranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6 etc., as well as individual numbers within that range, for example, 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

[0084] Whenever a numerical range is indicated herein, it is meant to include any cited numeral (fractional or integral) within the indicated range. The phrases “ranging / ranges between” a first indicate number and a second indicate number and “ranging / ranges from” a first indicate number “to” a second indicate number are used herein interchangeably and are meant to include the first and second indicated numbers and all the fractional and integral numerals therebetween.

[0085] It is appreciated that certain features, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features, which are, for brevity, described in the context ofa single embodiment, may also be provided separately or in any suitable subcombination or as suitable in any other described embodiment. Certain features described in the context of various embodiments are not to be considered essential features of those embodiments, unless the embodiment is inoperative without those elements.

[0086] Although the specific embodiments has been described, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, it is intended to embrace all such alternatives, modifications and variations that fall within the spirit and broad scope.

[0087] It is the intent of the applicant(s) that all publications, patents and patent applications referred to in this specification are to be incorporated in their entirety by reference into the specification, as if each individual publication, patent or patent application was specifically and individually noted when referenced that it is to be incorporated herein by reference. In addition, citation or identification of any reference in this application shall not be construed as an admission that such reference is available as prior art to the invention. To the extent that section headings are used, they should not be construed as necessarily limiting. In addition, any priority document(s) of this application is / are hereby incorporated herein by reference in its / their entirety.

Claims

CLAIMSWhat is claimed is:

1. A system, comprising: a plurality of wearable devices configured to be worn on a person's body, each wearable device comprising a microphone, a speaker and an antenna; a plurality of remote communication gateways and configured to enable transfer of the wireless signals from the antenna to a server and vice versa; and a server, comprising: a communication gateway configured to exchange signals with the multiple remote communication gateways; a memory for storing identifiers of wearable devices and a remote communication gateway of the multiple remote communication gateways associated with each of the multiple wearable devices; and a processor configured to: convert an audio signal received from a specific wearable device of the multiple wearable devices into text data; identify a task from the textual data; and create a feedback message to be sent to the specific wearable device via the specific remote communication gateway.

2. The system of claim 1 , wherein the specific remote communication gateway estimates a location of the specific wearable device.

3. The system of claim 2, wherein the processor generates a command message to be sent to a target account related to execution the task, wherein the command message comprises an identifier of the location.

4. The system of claim 2, wherein the specific remote communication gateway estimates the location based on signal strength and angle of arrival of the signal sent from the specific wearable device.

5. The system of claim 1, wherein the feedback message is an audio message.

6. The system of claim 1, wherein the task is identified as related to a medical condition and wherein the feedback message is created according to a treatment protocol for the identified medical condition.

7. The system of claim 1, wherein the processor is configured to identify whether the received audio signal relates to a new task or relates to a current task.

8. The system of claim 1, wherein the multiple wearable devices perform a roaming protocol configured to enable the multiple remote communication gateways to identify the wearable devices associated with each remote communication gateway.

9. The system of claim 1, wherein each wearable device comprising an accelerometer, wherein the server generates a falling event message in response to detection of abnormal readings by the accelerometer, wherein the server sends the falling event message to the wearable device that sent the abnormal reading, and wherein when the server identifies an insufficient response event from the wearable device the server sends an emergency message to an emergency account configured to handle a falling event.

10. A method, comprising: collecting audio signals from wearable devices via remote communication gateways; converting the audio signal received from a specific wearable device of the multiple wearable devices into text data; identifying a task from the textual data; creating a feedback message to be sent to the specific wearable device via the specific remote communication gateway; generating a command message to be sent to a target account related to execution the task, wherein the command message comprising an identifier of the location.

11. The method of claim 10, comprising identifying whether the message relates to a new task or old task.

12. The method of claim 10, comprising identifying similar requests in the person's history in a requests database; monitoring time elapsing from the similar request to the received message;in case the elapsing time is within a time frame of the person's medical condition, identify the message as relating to the similar request.

13. The method of claim 10, comprising computing the similarity between the extracted request and the request in the requests database by inputting vectors that represent text into a software model.

14. The method of claim 10, wherein identifying the similar request in case the similarity value between the extracted request and the request in the requests database is higher than a threshold.

15. The method of claim 10, comprising determining an urgency level of the extracted request based on a series of messages from the wearable device compared to a medical protocol and medical history of the patient.

16. The method of claim 10, comprising generating a falling event message in response to detection of abnormal readings by the accelerometer, sending the falling event message to the wearable device that sent the abnormal reading, identifying an insufficient response event from the wearable device, sending an emergency message to an emergency account configured to handle a falling event.

17. A system, comprising: a communication gateway configured to exchange signals with a plurality of wearable devices via multiple remote communication gateways; a memory for storing identifiers of a list of wearable devices and a remote communication gateway of the multiple remote communication gateways associated with each of the multiple wearable devices; a processor configured to: convert an audio signal received from a specific wearable device of the multiple wearable devices into text data; identify a task from the textual data; and create a feedback message to be sent to the specific wearable device via the specific remote communication gateway. 1

Images